Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нем
    -0.07
    帕
    -0.07
     snippets
    -0.07
    Critical
    -0.06
    raq
    -0.06
    kraine
    -0.06
    監督
    -0.06
    �
    -0.06
    특별
    -0.06
    919
    -0.06
    POSITIVE LOGITS
    sol
    0.06
     hete
    0.06
    alance
    0.06
     aba
    0.06
    iks
    0.06
    etik
    0.06
     Lean
    0.06
     Snackbar
    0.06
     Cab
    0.05
    SendMessage
    0.05
    Act Density 0.079%

    No Known Activations